> I also think it takes a lot of the fun out of the whole thing.

I used to say that implementation does not matter, tests should be your main focus. Now I treat every bit of code I wrote with my bare hands like a candy, agents have sucked the joy out of building things

Can we also take into account the mental cost associates with building software? Because how I see it, managing output from agents is way more exhausting than doing it ourself.

And obviously the cost of not upskilling in intricate technical details as much as before (aka staying at the high level perspective) will have to be paid at some point

It is pretty hard work huh! I was surprised. In my case, I was doing a personal project but in the end I felt a little crispy although the result was succesful.

Honestly now I only use agents for very narrow surgical scopes to avoid feeling numbed. It removed the fun of actually dreaming and building things

If only for the initiative driving the work behind delta-rs, I’d say it was well worth it!

> We don't need AGI (Artificial General Intelligence). We don't need a digital god. We just need software that works.

Yeah, I think the days of working software are over (at least deterministically)

Matches my experience also. Bothered only once to setup a proper CLAUDE.md file, and now never do it. Simply refering to the context properly for surgical recommendations and edit works relatively well.

It feels a lot like bikeshedding to me, maybe I’m wrong

> Coding is not fun anymore

The thing that made our crowd apart in the work society is now vanishing, that’s sad.

I wonder how future movies will depict programmers: depressed faces getting angrier and angrier chatting with a CLI coding agent! This will not inspire future generations!

Ever see the Fritz Lang’s metropolis? Like that but sitting down

Your daughter is so lucky! I meaning the physical UX is very reminiscent of teenage engineering, looks great! The more I was scrolling down the article the more I hoped for an « order » button :)

Until the product manager ask for the bill… then all of a sudden things get reconsidered

Yes using Python UDFs within Spark pipelines are a hog! That’s because the entire Python context is serialized with cloudpickle and sent over the wire to the executor nodes! (It can represent a few GB of serialized data depending on the UDF and driver process Python context)

Currently working on two OSS projects:

Laketower: https://github.com/datalpia/laketower A lightweight data lakehouse exploration and management app (web+cli), using DuckDB as the default query engine. It can run locally or self hosted, and for now statically configured only. Hope to integrate Iceberg and Ducklake support by end of year.

Modelship: https://github.com/datalpia/modelship An ML model to app generator. For now, only ONNX models are supported as input, and only static website as target (onnx runtime web wasm/webgpu). I intend to also work more on it the following weeks/months, especially to support more model I/O types, and add support for more targets (REST API, CLI, etc).

These 2 projects were born from professional activity needs but are a nice playground to learn and try new things